This paper evaluates the performance of six different machine learning (ML) algorithms for classifying power quality disturbances (PQDs), with statistical features extracted using discrete wavelet transform (DWT) as feature input. The statistical features have been extracted from coefficients of multi-resolution analysis (MRA) using four different mother wavelets: Daubechies 4 (‘db4’), ‘haar’, Discrete Meyer (‘dmey’), Coiflets 4 (‘coif4’). The performance analysis has been carried out with 5,500 synthetic signals pertaining to eleven different PQDs generated in accordance with IEEE 1159-2019. Moreover, the performance of the classifiers trained with synthetic signals has been investigated under the influence of unseen noisy signals, hardware PQD signals obtained from the experimental setup, and real PQD events. The analysis indicates that the performance of the extra tree (ET) classifier with the features extracted using ‘haar’ as a mother wavelet is superior and robust in comparison to other classifiers, viz k-nearest neighbor (kNN), random forest (RF), decision tree (DT), logistic regression model (LRM), and gaussian naïve bayes (GNB) with features extracted using different mother wavelets. Furthermore, the ‘haar-ET’ based technique demonstrated remarkable performance in classifying PQDs, showing strong generalization to both unseen hardware and noisy signals, and achieving consistent results when tested with real PQD events.

This paper presents work related to management of active and reactive power exchange between a distributed generation (DG) source and the grid to which it is connected; for improved utilization of electricity generated by the DG source such as solar energy. This is based on the recently introduced Availability Based Tariff (ABT) concept for the consumer loads, where conventional power grid is available. In situations, when, the grid power is available at high cost during high electrical tariff, the locally generated power from solar is utilized for consumer loads or even excess power can be fed back to the grid in order to earn financial benefits. On the other hand, during low electrical tariff, power generated is utilized for consumer loads or to charge batteries. Such system can also be utilized as Ancillary services for reactive power compensation, voltage control, loss compensation, energy imbalance etc.

An advanced IoT-based Liquefied Petroleum Gas (LPG) cylinder monitoring and safety system is presented in this work. The proposed technique provides continuous monitoring of residential gas usage and detects any potential leakage. It utilizes an MQ135 gas sensor for gas leakage detection, a load cell to monitor the weight of the cylinder, and a DHT22 sensor for temperature sensing. The sensors are mounted on a customized trolley for domestic LPG cylinders. All the sensors are connected to a NodeMCU microcontroller, which exchanges sensor data with a cloud platform using HTTP GET and POST methods to transmit the data to a cloud-based MySQL database. Unlike other existing methods, the proposed approach does not necessitate any modifications to the existing setup, which includes the gas cylinder, regulating valve, and distribution pipe. Furthermore, a mobile application that emphasizes the needs of the user is developed to enable a wider range of functionalities using cloud data collected from the sensors. The software facilitates the real-time monitoring of gas levels, provides comprehensive usage records for daily, weekly, and monthly intervals, issues immediate alarms in the event of gas leakage and low gas levels, and detects any unauthorized movement of the LPG cylinder, such as theft. The proposed technique not only improves user safety but also streamlines gas cylinder management with predictive analytics based on gas consumption trends and projected days of usage. Moreover, the application includes functionality that automatically orders a new cylinder with the vendor when the gas level drops below a predetermined threshold, therefore ensuring continuous availability of gas supply.

Power quality disturbances (PQDs) can significantly affect the reliability of electrical power systems, leading to potential equipment damage and operational inefficiencies. Accurate classification of these disturbances is essential for ensuring continuous and reliable service. The study proposes a deep transfer learning (TL) approach for PQD classification. In the proposed work, various single and multiple PQD signals pertaining to 15 different classes have been generated using mathematical models of PQDs adhering to the guidelines of the IEEE 1159 and IEC 61000-4-30 standards. Time-domain PQD signals are first converted into 2D color images using continuous wavelet transform (CWT). These images are then used to re-train modified pre-trained models such as GoogleNet, SqueezeNet, ResNet-18, and ShuffleNet on synthetic PQD data. Various single and combined PQDs are then classified using trained models. Moreover, the performance of the trained models is evaluated with the PQD signals containing noise of various signal-to-noise ratios (SNR), as well as PQD signals collected from the experimental setup in the laboratory. The results signify that the GoogleNet model exhibits consistent performance for classifying PQDs under various conditions, achieving classification accuracy of 99.8% for synthetic noiseless signals, 98.87% for signals with 20 dB SNR, and 98.89% for signals acquired through experimental setup. Furthermore, the trained models were tested using real-world PQD signals, comprising 26 sag and 42 impulse signals. The GoogleNet model achieved the highest classification accuracy, correctly identifying 23 sag and 34 impulse events, thereby demonstrating real-world applicability and robustness of the proposed approach.